André Luiz Pilastri

Bio: André Luiz Pilastri is an academic researcher from University of Minho. The author has contributed to research in topics: Computer science & Artificial intelligence. The author has an hindex of 4, co-authored 19 publications receiving 37 citations. Previous affiliations of André Luiz Pilastri include University of Porto.

A Comparison of AutoML Tools for Machine Learning, Deep Learning and XGBoost

Abstract: This paper presents a benchmark of supervised Automated Machine Learning (AutoML) tools. Firstly, we analyze the characteristics of eight recent open-source AutoML tools (Auto-Keras, Auto-PyTorch, Auto-Sklearn, AutoGluon, H2O AutoML, rminer, TPOT and TransmogrifAI) and describe twelve popular OpenML datasets that were used in the benchmark (divided into regression, binary and multi-class classification tasks). Then, we perform a comparison study with hundreds of computational experiments based on three scenarios: General Machine Learning (GML), Deep Learning (DL) and XGBoost (XGB). To select the best tool, we used a lexicographic approach, considering first the average prediction score for each task and then the computational effort. The best predictive results were achieved for GML, which were further compared with the best OpenML public results. Overall, the best GML AutoML tools obtained competitive results, outperforming the best OpenML models in five datasets. These results confirm the potential of the general-purpose AutoML tools to fully automate the Machine Learning (ML) algorithm selection and tuning.

Business analytics in industry 4.0: a systematic review

Abstract: The work of P. Cortez was supported by FCT - Fundacao para a Ciencia e Tecnologia within the R&D Units Project Scope: UIDB/00319/2020. We would like to thank to the three anonymous reviewers for their helpful suggestions.

Deep Dense and Convolutional Autoencoders for Unsupervised Anomaly Detection in Machine Condition Sounds.

Abstract: This technical report describes two methods that were developed for Task 2 of the DCASE 2020 challenge. The challenge involves an unsupervised learning to detect anomalous sounds, thus only normal machine working condition samples are available during the training process. The two methods involve deep autoencoders, based on dense and convolutional architectures that use melspectogram processed sound features. Experiments were held, using the six machine type datasets of the challenge. Overall, competitive results were achieved by the proposed dense and convolutional AE, outperforming the baseline challenge method.

An automated and distributed machine learning framework for telecommunications risk management

Abstract: This work was executed under the project IR-MDA - Intelligent Risk Management for the Digital Age, Individual Project, NUP: POCI-01-0247-FEDER-038526, co-funded by the Incentive Systemfor Research and Technological Development, fromthe Thematic Operational Program Competitivenessof the national framework program - Portugal2020.

Predicting the tear strength of woven fabrics via automated machine learning: an application of the CRISP-DM methodology

Abstract: Textile and clothing is an important world industry that is currently being transformed by the adoption of the Industry 4.0 concept. In this paper, we use Data Mining (DM) technology and the CRoss-Industry Standard Process for DM (CRISP-DM) methodology to model the textile testing process, which assures that products are safe and comply with regulations and client needs. Real-world data were collected from a Portuguese textile company, which has the goal to reduce the number of attempts they take in order to produce a woven fabric. Thus, predicting the outcome of a given test is beneficial to the company because it can reduce the number of physical samples that are needed to be produced when designing new fabrics. In particular, we target two important textile regression tasks: the tear strength in warp and weft directions. To better focus on feature engineering and data transformations, we adopt an Automated Machine Learning (AutoML) during the modeling stage of the CRISP-DM. Several iterations of the CRISP-DM methodology were employed, using different data preprocessing procedures (e.g., removal of outliers). The best predictive models were achieved after 2 (for warp) and 3 (for weft) CRISP-DM iterations.

MicroNets: Neural Network Architectures for Deploying TinyML Applications on Commodity Microcontrollers

Abstract: Executing machine learning workloads locally on resource constrained microcontrollers (MCUs) promises to drastically expand the application space of IoT. However, so-called TinyML presents severe technical challenges, as deep neural network inference demands a large compute and memory budget. To address this challenge, neural architecture search (NAS) promises to help design accurate ML models that meet the tight MCU memory, latency and energy constraints. A key component of NAS algorithms is their latency/energy model, i.e., the mapping from a given neural network architecture to its inference latency/energy on an MCU. In this paper, we observe an intriguing property of NAS search spaces for MCU model design: on average, model latency varies linearly with model operation (op) count under a uniform prior over models in the search space. Exploiting this insight, we employ differentiable NAS (DNAS) to search for models with low memory usage and low op count, where op count is treated as a viable proxy to latency. Experimental results validate our methodology, yielding our MicroNet models, which we deploy on MCUs using Tensorflow Lite Micro, a standard open-source NN inference runtime widely used in the TinyML community. MicroNets demonstrate state-of-the-art results for all three TinyMLperf industry-standard benchmark tasks: visual wake words, audio keyword spotting, and anomaly detection.

A Comparison of AutoML Tools for Machine Learning, Deep Learning and XGBoost

Abstract: This paper presents a benchmark of supervised Automated Machine Learning (AutoML) tools. Firstly, we analyze the characteristics of eight recent open-source AutoML tools (Auto-Keras, Auto-PyTorch, Auto-Sklearn, AutoGluon, H2O AutoML, rminer, TPOT and TransmogrifAI) and describe twelve popular OpenML datasets that were used in the benchmark (divided into regression, binary and multi-class classification tasks). Then, we perform a comparison study with hundreds of computational experiments based on three scenarios: General Machine Learning (GML), Deep Learning (DL) and XGBoost (XGB). To select the best tool, we used a lexicographic approach, considering first the average prediction score for each task and then the computational effort. The best predictive results were achieved for GML, which were further compared with the best OpenML public results. Overall, the best GML AutoML tools obtained competitive results, outperforming the best OpenML models in five datasets. These results confirm the potential of the general-purpose AutoML tools to fully automate the Machine Learning (ML) algorithm selection and tuning.

Trends in Compressive Sensing for EEG Signal Processing Applications.

Abstract: The tremendous progress of big data acquisition and processing in the field of neural engineering has enabled a better understanding of the patient's brain disorders with their neural rehabilitation, restoration, detection, and diagnosis. An integration of compressive sensing (CS) and neural engineering emerges as a new research area, aiming to deal with a large volume of neurological data for fast speed, long-term, and energy-saving purposes. Furthermore, electroencephalography (EEG) signals for brain-computer interfaces (BCIs) have shown to be very promising, with diverse neuroscience applications. In this review, we focused on EEG-based approaches which have benefited from CS in achieving fast and energy-saving solutions. In particular, we examine the current practices, scientific opportunities, and challenges of CS in the growing field of BCIs. We emphasized on summarizing major CS reconstruction algorithms, the sparse basis, and the measurement matrix used in CS to process the EEG signal. This literature review suggests that the selection of a suitable reconstruction algorithm, sparse basis, and measurement matrix can help to improve the performance of current CS-based EEG studies. In this paper, we also aim at providing an overview of the reconstruction free CS approach and the related literature in the field. Finally, we discuss the opportunities and challenges that arise from pushing the integration of the CS framework for BCI applications.

Review of ML and AutoML Solutions to Forecast Time-Series Data

Abstract: Time-series forecasting is a significant discipline of data modeling where past observations of the same variable are analyzed to predict the future values of the time series. Its prominence lies in different use cases where it is required, including economic, weather, stock price, business development, and other use cases. In this work, a review was conducted on the methods of analyzing time series starting from the traditional linear modeling techniques until the automated machine learning (AutoML) frameworks, including deep learning models. The objective of this review article is to support identifying the time-series forecasting challenge and the different techniques to meet the challenge. This work can be additionally an assist and a reference for researchers and industries demanding to use AutoML to solve the problem of forecasting. It identifies the gaps of the previous works and techniques used to solve the problem of forecasting time series.